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

    Neuronpedia

    INDEX
    Explanations

    combat environments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     camel
    -0.07
    BBC
    -0.07
    ב
    -0.07
    Sep
    -0.07
     proposition
    -0.07
    _APPRO
    -0.07
    .packet
    -0.07
    sav
    -0.07
    .Rad
    -0.07
     TNT
    -0.07
    POSITIVE LOGITS
     tq
    0.07
    Courier
    0.06
    �
    0.06
    σης
    0.06
     AttributeSet
    0.06
     그가
    0.06
    formulario
    0.06
    Enumeration
    0.06
    ouncer
    0.06
    ;


↵
    0.05
    Act Density 0.033%

    No Known Activations