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

    Neuronpedia

    INDEX
    Explanations

    ir

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attrs
    -0.07
     kaps
    -0.07
    Cele
    -0.07
    porno
    -0.07
    PUT
    -0.07
    Charge
    -0.07
    .MOD
    -0.06
    Las
    -0.06
    passed
    -0.06
    thumbs
    -0.06
    POSITIVE LOGITS
     крем
    0.07
     boycott
    0.06
     İz
    0.06
    主義
    0.06
     gerçek
    0.06
     [[]
    0.06
     Společ
    0.06
     undoubtedly
    0.06
     graphql
    0.06
     a
    0.06
    Act Density 0.000%

    No Known Activations