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

    Neuronpedia

    INDEX
    Explanations

    processor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olecule
    -0.06
     LM
    -0.06
     job
    -0.06
     смерти
    -0.06
    亡
    -0.06
    Hostname
    -0.06
     Clips
    -0.06
    _vis
    -0.06
    xAB
    -0.06
     кораб
    -0.06
    POSITIVE LOGITS
    lower
    0.07
     designate
    0.06
     microscope
    0.06
     peeled
    0.06
    SplitOptions
    0.06
    becue
    0.06
     bulls
    0.06
    ened
    0.06
    _mod
    0.06
     Slee
    0.06
    Act Density 0.001%

    No Known Activations