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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    感情
    -0.07
     binge
    -0.07
    _Base
    -0.07
     �
    -0.06
     stash
    -0.06
     ale
    -0.06
     hút
    -0.06
    iba
    -0.06
    Si
    -0.06
    Activated
    -0.06
    POSITIVE LOGITS
     باشگاه
    0.07
    .break
    0.07
    WARDS
    0.06
     =>{↵
    0.06
     返回
    0.06
     С
    0.06
    _host
    0.06
    시오
    0.06
     أكتوبر
    0.06
    )$/
    0.06
    Act Density 0.036%

    No Known Activations