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

    Neuronpedia

    INDEX
    Explanations

    liability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     predator
    -0.06
    BW
    -0.06
    _attached
    -0.06
    -related
    -0.06
    far
    -0.06
     terrifying
    -0.06
    315
    -0.06
     fear
    -0.06
    ToStr
    -0.06
     Sith
    -0.06
    POSITIVE LOGITS
     derive
    0.07
     limb
    0.06
     relying
    0.06
     Navy
    0.06
     cung
    0.06
     Lumpur
    0.06
     videos
    0.06
     बढ
    0.06
    -care
    0.06
     orth
    0.06
    Act Density 0.000%

    No Known Activations