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

    Neuronpedia

    INDEX
    Explanations

    hide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    니스
    -0.07
    ;";↵
    -0.06
    spawn
    -0.06
     между
    -0.06
    .Scan
    -0.06
    แก
    -0.06
     vocab
    -0.06
     fu
    -0.06
     rulers
    -0.06
     turno
    -0.06
    POSITIVE LOGITS
    輪
    0.07
    extracomment
    0.06
    ablytyped
    0.06
    ��
    0.06
     Tento
    0.06
     Japanese
    0.06
    hlas
    0.06
    eného
    0.06
     vý
    0.06
    ToSelector
    0.06
    Act Density 0.009%

    No Known Activations