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

    Neuronpedia

    INDEX
    Explanations

    sections related to installation and usage instructions in documentation

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

    explaining usage or syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vikipedi
    -0.55
    WebVitals
    -0.52
     Infórmanos
    -0.51
    帖最后由
    -0.51
    GraphicsUnit
    -0.50
    SharedCtor
    -0.49
    zzleHttp
    -0.48
    Спољашње
    -0.48
    rizona
    -0.47
    RTCF
    -0.46
    POSITIVE LOGITS
     StatefulWidget
    0.42
    bentar
    0.39
    Referències
    0.38
    abstractmethod
    0.38
     futuras
    0.37
    Tracce
    0.37
     precisamente
    0.36
    ตน
    0.35
     maravilla
    0.35
     precisely
    0.35
    Act Density 0.237%

    No Known Activations