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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intention
    -0.07
     stomach
    -0.06
     أبو
    -0.06
    _array
    -0.06
     organized
    -0.06
     expectations
    -0.06
    Win
    -0.06
    аст
    -0.06
     Juan
    -0.06
     waitress
    -0.06
    POSITIVE LOGITS
     CharSequence
    0.07
     sabot
    0.07
    OLTIP
    0.06
     Equ
    0.06
    邮
    0.06
    cstring
    0.06
    .FlatStyle
    0.06
     चर
    0.06
    angered
    0.06
    compileComponents
    0.06
    Act Density 0.205%

    No Known Activations