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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onces
    -0.07
    (verbose
    -0.07
    avr
    -0.07
     usize
    -0.07
     <->
    -0.07
    ₨
    -0.07
     overloaded
    -0.07
    ductive
    -0.07
    cmath
    -0.06
    -method
    -0.06
    POSITIVE LOGITS
    _RESP
    0.08
     GRID
    0.07
    lectron
    0.07
    .FileReader
    0.07
     patients
    0.07
    -g
    0.06
    候选人
    0.06
    宣言
    0.06
    זל
    0.06
    生产总
    0.06
    Act Density 0.010%

    No Known Activations