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

    Neuronpedia

    INDEX
    Explanations

    trial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     guidance
    -0.07
     Leben
    -0.07
    WithTitle
    -0.07
     Wallet
    -0.07
     freight
    -0.07
     että
    -0.07
     derecho
    -0.06
    以来
    -0.06
    -key
    -0.06
    umnos
    -0.06
    POSITIVE LOGITS
     LSU
    0.08
    ฝ
    0.07
    aul
    0.07
    .loadtxt
    0.06
    ,obj
    0.06
     ideology
    0.06
    _il
    0.06
     lol
    0.06
     �
    0.06
    .Min
    0.06
    Act Density 0.004%

    No Known Activations