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

    Neuronpedia

    INDEX
    Explanations

    prints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obed
    -0.07
    (single
    -0.07
    itesi
    -0.07
     Ortiz
    -0.07
    №
    -0.07
    vette
    -0.07
     oblast
    -0.06
    公園
    -0.06
     Islamabad
    -0.06
    .Substring
    -0.06
    POSITIVE LOGITS
     improvements
    0.07
    cient
    0.07
    ions
    0.07
     organisations
    0.07
     phases
    0.07
     looked
    0.06
    _bound
    0.06
     Extra
    0.06
     deposition
    0.06
     addition
    0.06
    Act Density 0.000%

    No Known Activations