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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     work
    -0.07
    -work
    -0.07
     tape
    -0.06
    怪
    -0.06
    -heading
    -0.06
     Nat
    -0.06
    -ar
    -0.06
    您的
    -0.06
    NX
    -0.06
    (('
    -0.06
    POSITIVE LOGITS
     음
    0.07
    .gameObject
    0.07
     meaningless
    0.07
     घटन
    0.06
    �
    0.06
     період
    0.06
     creampie
    0.06
    EQ
    0.06
     гром
    0.06
    .g
    0.06
    Act Density 0.004%

    No Known Activations