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

    Neuronpedia

    INDEX
    Explanations

    tool use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    0.54
     Freud
    0.53
    Type
    0.50
    Response
    0.48
    X
    0.47
     \
    0.45
    –
    0.44
    Br
    0.43
    Huge
    0.42
    Law
    0.42
    POSITIVE LOGITS
     fotografía
    0.57
     země
    0.52
     disminución
    0.49
     노력
    0.49
     resistência
    0.49
     коман
    0.48
     ética
    0.48
     sejam
    0.48
     pandemi
    0.48
     tantos
    0.48
    Act Density 0.001%

    No Known Activations