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

    Neuronpedia

    INDEX
    Explanations

    Planning permission

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Included
    -0.08
     clot
    -0.07
    ➟
    -0.07
     waive
    -0.06
    怖
    -0.06
    _clip
    -0.06
    .createTextNode
    -0.06
     localStorage
    -0.06
     cheese
    -0.06
     evil
    -0.06
    POSITIVE LOGITS
    不仅仅是
    0.07
    ��
    0.07
    partner
    0.07
     setters
    0.07
    دت
    0.07
    atego
    0.07
    AZE
    0.07
    edere
    0.07
    .override
    0.07
    תחת
    0.06
    Act Density 0.040%

    No Known Activations