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

    Neuronpedia

    INDEX
    Explanations

    minute

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vrais
    -0.53
     éditoriale
    -0.52
     vraie
    -0.52
    REMOV
    -0.52
     CURIAM
    -0.50
     aktivitet
    -0.50
    uangan
    -0.50
     ujednoznacz
    -0.50
     Leite
    -0.50
     gynhyrchwyd
    -0.49
    POSITIVE LOGITS
    "]));
    0.60
     مشين
    0.60
    ".
    0.60
    }{*}{}
    0.57
     RZ
    0.56
    "):
    0.56
    ”]
    0.56
    )”.
    0.55
    }';
    0.55
    `]
    0.54
    Act Density 0.009%

    No Known Activations