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

    Neuronpedia

    INDEX
    Explanations

    negative situations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (remote
    -0.06
     путем
    -0.06
    řím
    -0.06
     мг
    -0.06
    ować
    -0.06
     XI
    -0.06
    nictvím
    -0.06
     Dt
    -0.06
    Our
    -0.06
     pioneered
    -0.06
    POSITIVE LOGITS
    購
    0.07
     Workflow
    0.07
     SPDX
    0.06
     kultur
    0.06
     melan
    0.06
    وگر
    0.06
    -note
    0.06
    _Off
    0.06
    xeb
    0.06
     Exped
    0.06
    Act Density 0.065%

    No Known Activations