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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,no
    -0.07
    ในร
    -0.06
     basis
    -0.06
     ther
    -0.06
     auc
    -0.06
     brief
    -0.06
    .There
    -0.06
    uniform
    -0.06
    _and
    -0.06
    14
    -0.06
    POSITIVE LOGITS
    istine
    0.07
     Mal
    0.07
     तल
    0.07
    Mal
    0.07
     时
    0.07
     ẩm
    0.06
    .AppCompatActivity
    0.06
    ablytyped
    0.06
    作为
    0.06
     cherche
    0.06
    Act Density 0.052%

    No Known Activations