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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     macOS
    -0.06
    ظٹط
    -0.06
    unnable
    -0.06
    _java
    -0.06
     wine
    -0.06
    [k
    -0.06
     Mountains
    -0.06
     Goth
    -0.06
     stomach
    -0.06
    ileaks
    -0.06
    POSITIVE LOGITS
     유
    0.07
     hissed
    0.06
     trif
    0.06
     intercept
    0.06
     intercepted
    0.06
     infiltr
    0.06
    -Jul
    0.06
     اختی
    0.06
     ADVISED
    0.06
     Bruno
    0.06
    Act Density 0.100%

    No Known Activations