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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     몸
    -0.07
    inden
    -0.07
    _NUMERIC
    -0.06
    .IN
    -0.06
    .rnn
    -0.06
     findAll
    -0.06
    ink
    -0.06
     dhe
    -0.06
     vs
    -0.06
    γι
    -0.06
    POSITIVE LOGITS
     preca
    0.06
     Clearance
    0.06
     EOF
    0.06
    baar
    0.06
    afka
    0.06
    *****/↵
    0.05
    fell
    0.05
    лось
    0.05
    ijkstra
    0.05
     carousel
    0.05
    Act Density 0.007%

    No Known Activations