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

    Neuronpedia

    INDEX
    Explanations

    m

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kn
    -0.08
     gre
    -0.08
    їх
    -0.07
     RN
    -0.07
    styl
    -0.07
    _CONTACT
    -0.07
    ruh
    -0.06
    лан
    -0.06
     predictors
    -0.06
    atemala
    -0.06
    POSITIVE LOGITS
     bara
    0.07
     degli
    0.06
     своего
    0.06
     durch
    0.06
    _crypto
    0.06
     również
    0.06
     Brilliant
    0.06
     sice
    0.06
    자를
    0.06
    <Self
    0.06
    Act Density 0.063%

    No Known Activations