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

    Neuronpedia

    INDEX
    Explanations

    years of experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wooden
    0.59
    wooden
    0.59
    Wooden
    0.55
     झालेल्या
    0.53
    чер
    0.51
     Vampire
    0.48
     Watercolour
    0.47
    🚬
    0.47
     Joker
    0.47
     Motorcycle
    0.46
    POSITIVE LOGITS
     kog
    0.49
     deck
    0.48
    gia
    0.47
    x
    0.46
     cancels
    0.46
     heterod
    0.46
     grand
    0.45
     grandiose
    0.44
     coeff
    0.44
     coz
    0.44
    Act Density 0.000%

    No Known Activations