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

    Neuronpedia

    INDEX
    Explanations

    First person writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kinase
    -0.07
     longevity
    -0.07
    pattern
    -0.07
     HOUSE
    -0.06
     LE
    -0.06
     PRE
    -0.06
    PRE
    -0.06
    athy
    -0.06
    program
    -0.06
    electric
    -0.06
    POSITIVE LOGITS
     darüber
    0.07
    atts
    0.06
     olab
    0.06
    FD
    0.06
     dashes
    0.06
     вред
    0.06
     करन
    0.06
    —who
    0.06
    Ns
    0.06
    =args
    0.06
    Act Density 0.150%

    No Known Activations