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

    Neuronpedia

    INDEX
    Explanations

    Possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Act
    -0.06
     Myth
    -0.06
    (Op
    -0.06
    ++;
↵
    -0.06
     Carson
    -0.06
    (Component
    -0.06
    jah
    -0.06
    _MEMBER
    -0.06
    _unset
    -0.05
    ContentView
    -0.05
    POSITIVE LOGITS
     قب
    0.08
     може
    0.07
     почему
    0.07
     facilitating
    0.07
     стены
    0.07
     schema
    0.07
     depuis
    0.07
     بط
    0.06
     Rewrite
    0.06
    iffs
    0.06
    Act Density 0.027%

    No Known Activations