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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leans
    -0.08
     muže
    -0.07
    UseProgram
    -0.07
     Piano
    -0.07
    boru
    -0.06
     пош
    -0.06
     lem
    -0.06
     UIPickerView
    -0.06
    Var
    -0.06
    [sizeof
    -0.06
    POSITIVE LOGITS
    events
    0.07
    -eslint
    0.07
     partnerships
    0.07
    ificance
    0.07
    mailbox
    0.07
    pod
    0.06
    ddit
    0.06
    оды
    0.06
    _BATCH
    0.06
     wellbeing
    0.06
    Act Density 0.000%

    No Known Activations