Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of decision-making and opportunities related to job positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    now here, now rewired

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Signalez
    -0.45
     tartalomajánló
    -0.41
     otomatig
    -0.38
    atoires
    -0.35
    CloseOperation
    -0.35
     الحره
    -0.33
    ificados
    -0.33
    tvguidetime
    -0.33
    \{\\
    -0.33
     Masyarakat
    -0.33
    POSITIVE LOGITS
    enderror
    0.54
    ፩
    0.50
    /**
    0.47
    domada
    0.46
    SourceChecksum
    0.46
    amsmath
    0.46
    parsedMessage
    0.46
    abstractmethod
    0.46
    uscular
    0.45
    getMenuInflater
    0.45
    Act Density 0.373%

    No Known Activations