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

    Neuronpedia

    INDEX
    Explanations

    arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kissed
    -0.06
     Bridges
    -0.06
     Kingdom
    -0.06
     Isle
    -0.06
    单位
    -0.06
    /me
    -0.06
    OMETRY
    -0.06
     came
    -0.06
    K
    -0.05
    *******
    -0.05
    POSITIVE LOGITS
     searching
    0.07
     Reyn
    0.07
    <HTMLInputElement
    0.06
    شار
    0.06
    _APPLICATION
    0.06
     UAV
    0.06
     feat
    0.06
    .DATE
    0.06
    (fin
    0.06
     iter
    0.06
    Act Density 0.016%

    No Known Activations