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

    Neuronpedia

    INDEX
    Explanations

    measurement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    רב
    -0.07
    athi
    -0.07
    FUNC
    -0.06
    gatsby
    -0.06
    _main
    -0.06
     Connect
    -0.06
    忻
    -0.06
    _intr
    -0.06
    火灾
    -0.06
     Load
    -0.06
    POSITIVE LOGITS
     menor
    0.07
    incess
    0.07
     הבע
    0.07
    —but
    0.06
     украин
    0.06
     broker
    0.06
     nhắc
    0.06
    瞽
    0.06
    (factor
    0.06
     gaz
    0.06
    Act Density 0.064%

    No Known Activations