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

    Neuronpedia

    INDEX
    Explanations

    registration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     मन
    -0.08
     слова
    -0.07
    -around
    -0.07
     partir
    -0.07
    LD
    -0.07
    Arm
    -0.07
     Leaders
    -0.07
    Session
    -0.07
     organisation
    -0.07
     map
    -0.07
    POSITIVE LOGITS
     gön
    0.06
     Eins
    0.06
    :none
    0.06
    кон
    0.06
    selectorMethod
    0.06
    storms
    0.06
     liar
    0.06
    859
    0.06
    ادية
    0.06
    �
    0.06
    Act Density 0.054%

    No Known Activations