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

    Neuronpedia

    INDEX
    Explanations

    Action and planning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dollar
    -0.07
    uite
    -0.07
    <C
    -0.07
    .query
    -0.06
    หล
    -0.06
    Captain
    -0.06
     cops
    -0.06
    olation
    -0.06
    __,__
    -0.06
     dao
    -0.06
    POSITIVE LOGITS
     nós
    0.07
     Reno
    0.06
     republik
    0.06
     Interactive
    0.06
    rogram
    0.06
    ż
    0.06
     없었다
    0.06
    MOD
    0.06
     забезпечення
    0.06
    =require
    0.06
    Act Density 0.020%

    No Known Activations