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

    Neuronpedia

    INDEX
    Explanations

    relevant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tekn
    -0.07
    ({'
    -0.06
    фт
    -0.06
     Pin
    -0.06
     segregation
    -0.06
    uth
    -0.06
    insn
    -0.06
    ais
    -0.06
    gist
    -0.06
    _ml
    -0.06
    POSITIVE LOGITS
    _arrow
    0.07
    select
    0.07
    ..
    0.06
     keto
    0.06
    	expect
    0.06
    [cur
    0.06
     comet
    0.06
     Gene
    0.06
     Jeremy
    0.06
    Section
    0.06
    Act Density 0.014%

    No Known Activations