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

    Neuronpedia

    INDEX
    Explanations

    coaching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LANGUAGE
    -0.07
     probabil
    -0.06
     fChain
    -0.06
     servlet
    -0.06
    ared
    -0.06
     controle
    -0.06
    скільки
    -0.06
    .op
    -0.06
    ursos
    -0.06
     SPL
    -0.06
    POSITIVE LOGITS
     films
    0.07
     Films
    0.06
     Post
    0.06
    /images
    0.06
    Implemented
    0.06
     aircraft
    0.06
     कहत
    0.06
    MENT
    0.06
     Fish
    0.06
    Fish
    0.06
    Act Density 0.000%

    No Known Activations