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

    Neuronpedia

    INDEX
    Explanations

    building blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rale
    0.52
     befri
    0.48
     outraged
    0.47
     చ
    0.47
    atir
    0.45
    されない
    0.44
     muted
    0.44
     reassuring
    0.44
    దల
    0.42
    బర్
    0.42
    POSITIVE LOGITS
     bezpośred
    0.50
     ذمہ
    0.50
     wszystkie
    0.49
    Existing
    0.48
    Built
    0.47
    CEPTION
    0.47
     anteriormente
    0.47
     insanın
    0.47
     iyong
    0.47
    NOTIFICATION
    0.46
    Act Density 0.000%

    No Known Activations