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

    Neuronpedia

    INDEX
    Explanations

    say then

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Level
    -0.06
    _lvl
    -0.06
     市
    -0.06
     Macro
    -0.06
     backpage
    -0.06
    List
    -0.06
     fotoğraf
    -0.06
    ("--------------------------------
    -0.06
    .ToolTip
    -0.06
     Americas
    -0.06
    POSITIVE LOGITS
    ойно
    0.07
    axon
    0.07
     перег
    0.07
    alm
    0.06
    ulse
    0.06
     pushing
    0.06
    UBL
    0.06
     equiv
    0.06
    vál
    0.06
    ULATE
    0.06
    Act Density 0.120%

    No Known Activations