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

    Neuronpedia

    INDEX
    Explanations

    technical, mathematical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fores
    -0.07
     dost
    -0.07
     useful
    -0.07
    guna
    -0.07
     nit
    -0.06
     cuanto
    -0.06
    atical
    -0.06
     hele
    -0.06
     ह
    -0.06
    	resp
    -0.06
    POSITIVE LOGITS
    昭和
    0.06
    .UndefOr
    0.06
    _Response
    0.06
    METHOD
    0.06
     百度收录
    0.06
     amendments
    0.06
     founders
    0.06
    Candidate
    0.06
     CLIIIK
    0.06
     oğlu
    0.05
    Act Density 0.102%

    No Known Activations