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

    Neuronpedia

    INDEX
    Explanations

    possible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    filled
    -0.07
    zn
    -0.07
    titleLabel
    -0.07
     daddy
    -0.07
     controller
    -0.07
     Hear
    -0.07
     aluminium
    -0.07
     titleLabel
    -0.07
    -host
    -0.07
    Deadline
    -0.07
    POSITIVE LOGITS
    外援
    0.07
    𝛾
    0.07
    �
    0.07
    ],'
    0.07
    .android
    0.07
    촤
    0.07
    ("../
    0.07
    ።
    0.07
    .pg
    0.06
     그러
    0.06
    Act Density 0.087%

    No Known Activations