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

    Neuronpedia

    INDEX
    Explanations

    way

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ngen
    -0.07
     조금
    -0.06
     dirname
    -0.06
    acist
    -0.06
    .GenerationType
    -0.06
    ственным
    -0.06
     yaptığ
    -0.06
     arrog
    -0.06
    ignored
    -0.06
     Mitar
    -0.06
    POSITIVE LOGITS
    	utils
    0.06
    Sony
    0.06
    تق
    0.06
     sided
    0.06
     travelers
    0.06
    -character
    0.06
    uber
    0.06
    [label
    0.06
    Smith
    0.06
    .expression
    0.06
    Act Density 0.000%

    No Known Activations