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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    алися
    -0.07
     binder
    -0.07
    不
    -0.07
     市
    -0.06
     труб
    -0.06
    _owner
    -0.06
    rate
    -0.06
    _routes
    -0.06
    Enc
    -0.06
     newArray
    -0.06
    POSITIVE LOGITS
     основных
    0.07
     "~
    0.07
     von
    0.07
     oyuncu
    0.07
     Supported
    0.07
    .DE
    0.06
     Naked
    0.06
     mbox
    0.06
    ξεις
    0.06
    .ft
    0.06
    Act Density 0.003%

    No Known Activations