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

    Neuronpedia

    INDEX
    Explanations

    phrases with "and their"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dos
    0.48
    ら
    0.47
    MCs
    0.46
     πίνακα
    0.46
    odin
    0.45
     individus
    0.45
    ק
    0.45
    g
    0.44
     BUSINESS
    0.43
    ล
    0.43
    POSITIVE LOGITS
     Medio
    0.51
     GridSearchCV
    0.48
     Mage
    0.45
     Flugh
    0.45
    irstyle
    0.43
     Diario
    0.43
     Česk
    0.43
     Wake
    0.42
     Jefe
    0.42
     worst
    0.42
    Act Density 0.010%

    No Known Activations