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

    Neuronpedia

    INDEX
    Explanations

    code exclusion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Repositories
    -0.07
    tones
    -0.07
     Fuck
    -0.06
    ść
    -0.06
    folk
    -0.06
    ibNameOrNil
    -0.06
     dictates
    -0.06
    انات
    -0.06
     ccp
    -0.06
    Show
    -0.06
    POSITIVE LOGITS
     Behaviour
    0.07
    _hw
    0.07
    .lock
    0.07
     activations
    0.07
     Adelaide
    0.07
     acceler
    0.07
     Behavior
    0.07
    Echo
    0.06
    筑
    0.06
    аліст
    0.06
    Act Density 0.040%

    No Known Activations