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
     sonra
    -0.07
    lom
    -0.06
    OAD
    -0.06
    _jump
    -0.06
    陽
    -0.06
     оз
    -0.06
     Table
    -0.06
    achuset
    -0.06
    _fh
    -0.06
    人間
    -0.06
    POSITIVE LOGITS
     ammunition
    0.07
    /dev
    0.07
     laundering
    0.07
     Le
    0.07
     нужно
    0.06
    .Imp
    0.06
     Dominic
    0.06
    SUCCESS
    0.06
    erva
    0.06
     MT
    0.06
    Act Density 0.183%

    No Known Activations