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

    Neuronpedia

    INDEX
    Explanations

    code configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sidelines
    -0.07
    (comm
    -0.07
     child
    -0.06
    '",
    -0.06
     neuken
    -0.06
    ifter
    -0.06
     wrists
    -0.06
    UpEdit
    -0.06
    .commands
    -0.06
     otro
    -0.06
    POSITIVE LOGITS
    dere
    0.07
    Pid
    0.06
    睛
    0.06
    ascending
    0.06
    iterr
    0.06
    Honda
    0.06
     اش
    0.06
    CISION
    0.06
    Bean
    0.06
     Peru
    0.06
    Act Density 0.063%

    No Known Activations