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

    Neuronpedia

    INDEX
    Explanations

    their

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DBG
    -0.07
    しても
    -0.07
     Cheng
    -0.07
     Per
    -0.07
     writings
    -0.07
    "]=
    -0.07
    Frank
    -0.06
     condemnation
    -0.06
    .safe
    -0.06
     Current
    -0.06
    POSITIVE LOGITS
    enticator
    0.06
    roller
    0.06
     بسي
    0.06
     무슨
    0.06
     impacts
    0.06
    erville
    0.06
     jav
    0.06
    нг
    0.06
    UniformLocation
    0.06
    pressor
    0.06
    Act Density 0.000%

    No Known Activations