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

    Neuronpedia

    INDEX
    Explanations

    comparisons, descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spoiled
    -0.07
    ίσω
    -0.07
    ğim
    -0.06
     Escape
    -0.06
     casualties
    -0.06
    ptom
    -0.06
    reach
    -0.06
    ifying
    -0.06
     maximizing
    -0.06
    attack
    -0.06
    POSITIVE LOGITS
    _pop
    0.07
    val
    0.07
     décou
    0.06
    IND
    0.06
     unsus
    0.06
     ".$
    0.06
    IntArray
    0.06
    DOWNLOAD
    0.06
    .netty
    0.06
     klein
    0.06
    Act Density 0.089%

    No Known Activations