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

    Neuronpedia

    INDEX
    Explanations

    /plain

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ITER
    -0.07
    _bd
    -0.07
    iller
    -0.07
    >]
    -0.07
    עסוק
    -0.06
    肇事
    -0.06
    عقد
    -0.06
    ☰
    -0.06
    눗
    -0.06
    污
    -0.06
    POSITIVE LOGITS
    ymmetric
    0.06
    	static
    0.06
    ogy
    0.06
    -fw
    0.06
    aaS
    0.06
    族
    0.06
     anthropology
    0.06
     heroes
    0.06
     rex
    0.06
     większo
    0.06
    Act Density 0.000%

    No Known Activations