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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Caribbean
    -0.07
    Direction
    -0.06
    =context
    -0.06
    Destroy
    -0.06
     Hwy
    -0.06
    集团
    -0.06
     rubbed
    -0.06
    Password
    -0.06
    Probability
    -0.06
    Verb
    -0.06
    POSITIVE LOGITS
    :<?
    0.07
    Latch
    0.07
     problem
    0.06
     masturbating
    0.06
     pojist
    0.06
    ICS
    0.06
     GRE
    0.06
    blah
    0.06
     LOD
    0.06
    >=
    0.06
    Act Density 0.000%

    No Known Activations