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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Append
    -0.07
    .school
    -0.06
    .So
    -0.06
    -build
    -0.06
    .Pin
    -0.06
    _SKIP
    -0.06
    aturdays
    -0.06
     roli
    -0.06
    WHO
    -0.06
    ホ
    -0.06
    POSITIVE LOGITS
     awarded
    0.07
    iya
    0.06
    omination
    0.06
    /native
    0.06
     magically
    0.06
     должен
    0.06
     매매
    0.06
    erialization
    0.06
     subsequent
    0.06
    略
    0.06
    Act Density 0.000%

    No Known Activations