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

    Neuronpedia

    INDEX
    Explanations

    counting characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     geometry
    -0.10
     Associate
    -0.09
     power
    -0.09
     ancillary
    -0.08
     gerar
    -0.08
     supremacy
    -0.08
     Associates
    -0.08
     companionship
    -0.08
     Deux
    -0.07
     matrices
    -0.07
    POSITIVE LOGITS
    Start
    0.08
    Analy
    0.08
    Sport
    0.08
    String
    0.08
     започ
    0.08
    Spaces
    0.08
    =s
    0.08
     попроб
    0.08
    гор
    0.08
     spelled
    0.08
    Act Density 0.009%

    No Known Activations