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

    Neuronpedia

    INDEX
    Explanations

    definition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urlencoded
    -0.47
    Q
    -0.44
    src
    -0.40
    TimerTask
    -0.40
     gäller
    -0.40
    ваку
    -0.39
     He
    -0.39
    ועל
    -0.38
    aryen
    -0.37
    W
    -0.37
    POSITIVE LOGITS
     Monfieur
    0.84
     &___
    0.75
     ſeveral
    0.72
     debout
    0.71
     ſtate
    0.70
    balleur
    0.70
     laſt
    0.68
     aient
    0.68
    ResumeLayout
    0.66
    complexContent
    0.66
    Act Density 0.003%

    No Known Activations