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

    Neuronpedia

    INDEX
    Explanations

    slash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Polynomial
    -0.08
     Glover
    -0.08
     nomine
    -0.07
    ็ด
    -0.07
     CGSizeMake
    -0.07
    Buffer
    -0.07
    动人
    -0.07
     Consort
    -0.07
     announc
    -0.07
    高压
    -0.07
    POSITIVE LOGITS
     permissions
    0.07
    }{$
    0.07
    	Type
    0.07
     eid
    0.07
    我说
    0.07
    ılması
    0.07
     endoth
    0.07
    igma
    0.07
    [list
    0.07
    部門
    0.07
    Act Density 0.009%

    No Known Activations