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

    Neuronpedia

    INDEX
    Explanations

    kilogram, fingerprint, and ice cube

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     நிமிட
    0.50
     большо
    0.50
    when
    0.48
    ığında
    0.48
    When
    0.48
     claridad
    0.47
     when
    0.46
     When
    0.46
     когда
    0.46
     noved
    0.46
    POSITIVE LOGITS
     or
    0.40
    之中
    0.39
     renom
    0.39
    或
    0.38
     berühm
    0.37
    uther
    0.37
    证券投资基金业协会
    0.36
    warts
    0.36
     loans
    0.35
    FieldError
    0.35
    Act Density 0.005%

    No Known Activations