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

    Neuronpedia

    INDEX
    Explanations

    formula

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ivalence
    -0.07
    _pol
    -0.07
     collapse
    -0.07
    "]->
    -0.06
     retreat
    -0.06
     conference
    -0.06
     distingu
    -0.06
     binder
    -0.06
    HN
    -0.06
     sections
    -0.06
    POSITIVE LOGITS
     formulas
    0.11
    formula
    0.08
    لو
    0.07
     formula
    0.06
    _formula
    0.06
     UIStoryboard
    0.06
    迹
    0.06
    _REALTYPE
    0.06
    Formula
    0.06
    _expr
    0.06
    Act Density 0.005%

    No Known Activations