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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IIC
    -0.07
     surround
    -0.07
     PVC
    -0.07
    "Well
    -0.07
    getView
    -0.06
    六
    -0.06
     landmark
    -0.06
     Mec
    -0.06
     reaction
    -0.06
    ай
    -0.06
    POSITIVE LOGITS
    ofile
    0.06
    чика
    0.06
    �
    0.06
    oman
    0.06
     Compiler
    0.06
    λε
    0.06
     ej
    0.06
     acad
    0.05
     Vega
    0.05
     Secret
    0.05
    Act Density 0.001%

    No Known Activations