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

    Neuronpedia

    INDEX
    Explanations

    ligaments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     embedding
    -0.07
    HOLDER
    -0.07
     Cooler
    -0.07
     naprost
    -0.06
     Off
    -0.06
     bj
    -0.06
    _OFF
    -0.06
     pk
    -0.06
     grote
    -0.06
     '\''
    -0.06
    POSITIVE LOGITS
    tain
    0.07
    (Item
    0.06
     différent
    0.06
    ponent
    0.06
    _PLUGIN
    0.06
     tend
    0.06
    licant
    0.06
    SWEP
    0.06
     Ident
    0.06
    .wik
    0.06
    Act Density 0.003%

    No Known Activations