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

    Neuronpedia

    INDEX
    Explanations

    code and documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dip
    -0.06
     adrenaline
    -0.06
    acements
    -0.06
     elaborate
    -0.06
    بة
    -0.06
    调查
    -0.06
     vardı
    -0.06
     decrease
    -0.06
    acente
    -0.06
     хроничес
    -0.06
    POSITIVE LOGITS
    .sock
    0.07
    [ii
    0.07
    izzy
    0.07
    ]?
    0.07
    ,res
    0.06
    yclerView
    0.06
     objeto
    0.06
     inkl
    0.06
     Brake
    0.06
    (policy
    0.06
    Act Density 0.000%

    No Known Activations