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

    Neuronpedia

    INDEX
    Explanations

    intervention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Two
    -0.07
    edish
    -0.07
    Atual
    -0.06
    Symbols
    -0.06
     Swedish
    -0.06
    favor
    -0.06
    Chinese
    -0.06
    장이
    -0.06
     val
    -0.06
    _Obj
    -0.06
    POSITIVE LOGITS
    .hp
    0.07
    /back
    0.06
     especific
    0.06
    ])
↵
↵
    0.06
    ,__
    0.06
    .Exp
    0.06
    >')↵
    0.06
     ACK
    0.06
    _LOADED
    0.06
     GLint
    0.06
    Act Density 0.031%

    No Known Activations