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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cấp
    -0.08
    ady
    -0.07
     Brief
    -0.07
    afe
    -0.07
    IES
    -0.07
    由
    -0.07
     Synopsis
    -0.06
     cosm
    -0.06
    𝘴
    -0.06
     Cyc
    -0.06
    POSITIVE LOGITS
    '||
    0.07
    _errors
    0.07
    ᴻ
    0.07
    "]);
    0.07
     elsif
    0.07
    -paper
    0.07
    .AR
    0.07
    ']>;↵
    0.06
     prompting
    0.06
    кам
    0.06
    Act Density 0.036%

    No Known Activations