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

    Neuronpedia

    INDEX
    Explanations

    say "hearing"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     embraces
    -0.07
    Cars
    -0.06
    Tracker
    -0.06
     futuristic
    -0.06
    Clearly
    -0.06
    /customer
    -0.06
     Ampl
    -0.06
    _access
    -0.06
     contradiction
    -0.06
    UTURE
    -0.06
    POSITIVE LOGITS
     머
    0.07
     Creat
    0.06
    余
    0.06
     मश
    0.06
     разм
    0.06
     ผล
    0.06
     opr
    0.06
     Sens
    0.06
    FIT
    0.06
     đỏ
    0.06
    Act Density 0.001%

    No Known Activations