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

    Neuronpedia

    INDEX
    Explanations

    seemed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Encode
    -0.08
     strings
    -0.07
     dolphins
    -0.07
    .WRITE
    -0.07
     cipher
    -0.07
    /problem
    -0.06
     \"$
    -0.06
    Reminder
    -0.06
     qreal
    -0.06
     samsung
    -0.06
    POSITIVE LOGITS
    Prototype
    0.06
     inj
    0.06
    ítulo
    0.06
     QUE
    0.06
     LOGIN
    0.06
    ãn
    0.06
    adden
    0.06
    ρα
    0.06
    zeň
    0.06
    왕
    0.05
    Act Density 0.205%

    No Known Activations