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

    Neuronpedia

    INDEX
    Explanations

    gain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ΡΙ
    -0.07
     escre
    -0.07
    verter
    -0.07
     perpetr
    -0.07
    不
    -0.07
     revolver
    -0.06
     Methodist
    -0.06
     contempt
    -0.06
     perpetrated
    -0.06
    filepath
    -0.06
    POSITIVE LOGITS
     gained
    0.18
     gain
    0.18
     gaining
    0.17
     Gain
    0.15
     gains
    0.12
    Gain
    0.12
    gain
    0.09
     regain
    0.09
     glean
    0.09
    AIN
    0.08
    Act Density 0.016%

    No Known Activations