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

    Neuronpedia

    INDEX
    Explanations

    technical manuals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quake
    -0.07
    yect
    -0.07
     accomplishments
    -0.07
     grounded
    -0.07
    /qt
    -0.06
    維
    -0.06
     forcefully
    -0.06
     پول
    -0.06
     Among
    -0.06
    /class
    -0.06
    POSITIVE LOGITS
     Wander
    0.07
    682
    0.06
    NDAR
    0.06
     baktı
    0.06
    Т
    0.06
    	ss
    0.06
    ு
    0.06
    ARR
    0.05
    Merge
    0.05
     alespoň
    0.05
    Act Density 0.336%

    No Known Activations