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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﳝ
    -0.08
     chevy
    -0.07
    𪨰
    -0.07
    Ɯ
    -0.07
    𫄧
    -0.07
    以
    -0.07
     ModelRenderer
    -0.07
    ider
    -0.07
     ي
    -0.07
     dout
    -0.06
    POSITIVE LOGITS
    (sequence
    0.08
    (encoded
    0.07
    ורך
    0.07
    裸
    0.07
    _art
    0.07
    军团
    0.07
    acct
    0.07
     Connection
    0.07
     funktion
    0.06
    _challenge
    0.06
    Act Density 0.020%

    No Known Activations