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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kred
    -0.07
    わ
    -0.07
     interruptions
    -0.06
    ほ
    -0.06
    .getHost
    -0.06
     Outlet
    -0.06
    _ARR
    -0.06
     homeless
    -0.06
     paste
    -0.06
            
    -0.06
    POSITIVE LOGITS
    thag
    0.07
    iliği
    0.07
    ?',
    0.06
     PLEASE
    0.06
    ượt
    0.06
     mg
    0.06
    argest
    0.06
    ρεια
    0.06
    ětí
    0.06
    childs
    0.06
    Act Density 0.386%

    No Known Activations