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

    Neuronpedia

    INDEX
    Explanations

    caregiving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ною
    -0.07
     proprietor
    -0.07
     Pf
    -0.07
    สำเร
    -0.07
    _publisher
    -0.07
     stripes
    -0.06
    .setScene
    -0.06
    Compet
    -0.06
     地
    -0.06
    .bucket
    -0.06
    POSITIVE LOGITS
    bell
    0.06
    untime
    0.06
    :[↵
    0.06
     Max
    0.06
    lean
    0.06
    _dbg
    0.06
     fp
    0.06
    quit
    0.06
     сообщ
    0.06
     nicely
    0.06
    Act Density 0.026%

    No Known Activations