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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cosa
    -0.07
     REST
    -0.07
    Constants
    -0.06
     j
    -0.06
     //////
    -0.06
    _CANNOT
    -0.06
     za
    -0.06
    _PRE
    -0.06
     ts
    -0.06
    owards
    -0.06
    POSITIVE LOGITS
     about
    0.07
     Waves
    0.07
    ift
    0.07
     envelope
    0.06
     About
    0.06
    Leod
    0.06
     bred
    0.06
    ager
    0.06
    affle
    0.06
    iver
    0.06
    Act Density 0.003%

    No Known Activations