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

    Neuronpedia

    INDEX
    Explanations

    creating something (computer)

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     templates
    -0.08
    ʕ
    -0.07
    _SELECT
    -0.07
     polite
    -0.07
    ǎ
    -0.07
    _trampoline
    -0.07
    ᡡ
    -0.06
     tap
    -0.06
    -click
    -0.06
     Choose
    -0.06
    POSITIVE LOGITS
     ['-
    0.07
     Natürlich
    0.07
    لا
    0.07
     KY
    0.07
            
↵        
↵
    0.07
     Joined
    0.07
     monitored
    0.06
    getVar
    0.06
    Joined
    0.06
            ↵        ↵
    0.06
    Act Density 0.032%

    No Known Activations