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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Metal
    -0.08
    't
    -0.07
    -metal
    -0.06
     Da
    -0.06
     Zhang
    -0.06
     Situation
    -0.06
     dusk
    -0.06
     Jordan
    -0.06
     funct
    -0.06
     Tooth
    -0.06
    POSITIVE LOGITS
    _style
    0.07
    ARIANT
    0.06
    BorderStyle
    0.06
     ^=
    0.06
    DebugEnabled
    0.06
    (World
    0.06
    اعد
    0.06
    سه
    0.06
     вед
    0.06
    :ss
    0.06
    Act Density 0.007%

    No Known Activations