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

    Neuronpedia

    INDEX
    Explanations

    clutch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    //-
    -0.07
     waivers
    -0.07
     birey
    -0.07
     flowed
    -0.07
     版
    -0.07
     famine
    -0.06
    inear
    -0.06
     天
    -0.06
    езда
    -0.06
     bouncing
    -0.06
    POSITIVE LOGITS
     clutch
    0.13
    .collections
    0.08
    Let
    0.07
     MUCH
    0.07
     vš
    0.06
    utch
    0.06
    retched
    0.06
    LTR
    0.06
    utches
    0.06
    ।↵
    0.06
    Act Density 0.001%

    No Known Activations