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

    Neuronpedia

    INDEX
    Explanations

    forum comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (idx
    -0.07
    geber
    -0.06
    _member
    -0.06
     circumstances
    -0.06
    unden
    -0.06
     Мініст
    -0.06
     southern
    -0.06
    еса
    -0.06
    .Run
    -0.06
    <Base
    -0.06
    POSITIVE LOGITS
     قص
    0.06
    _PRO
    0.06
    @Configuration
    0.06
     climax
    0.06
     Cardinal
    0.06
     grips
    0.06
    obbled
    0.06
    aby
    0.06
     beforeEach
    0.06
     行
    0.06
    Act Density 0.006%

    No Known Activations