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

    Neuronpedia

    INDEX
    Explanations

    days

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bjerg
    -0.07
     tightly
    -0.07
    äm
    -0.07
     گروه
    -0.06
    umhur
    -0.06
    %
    -0.06
    lemma
    -0.06
    SCAN
    -0.06
    _k
    -0.06
     ©
    -0.06
    POSITIVE LOGITS
     IRC
    0.07
    επ
    0.06
     tame
    0.06
     honorable
    0.06
    대의
    0.06
    _chain
    0.06
    veral
    0.06
    irectory
    0.06
     Documents
    0.06
     simplicity
    0.06
    Act Density 0.020%

    No Known Activations