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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NSNotification
    -0.07
    (solution
    -0.06
    ham
    -0.06
    postalcode
    -0.06
     mostly
    -0.06
    เ
    -0.06
    brtc
    -0.06
    aceutical
    -0.06
    nom
    -0.05
    ziel
    -0.05
    POSITIVE LOGITS
     placement
    0.07
     Crazy
    0.07
     |-
    0.06
     quiere
    0.06
    _ex
    0.06
    芝
    0.06
    _queue
    0.06
     ancestry
    0.06
     Σε
    0.06
     Aly
    0.06
    Act Density 0.003%

    No Known Activations