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

    Neuronpedia

    INDEX
    Explanations

    home

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TLS
    -0.06
    /></
    -0.06
    ess
    -0.06
    apollo
    -0.06
        
    -0.06
    SMS
    -0.05
    ccess
    -0.05
    nat
    -0.05
    	url
    -0.05
    .url
    -0.05
    POSITIVE LOGITS
     стак
    0.07
    ，在
    0.07
    面积
    0.07
     온라인
    0.07
    -earth
    0.07
     protest
    0.06
     одну
    0.06
     penalty
    0.06
    frage
    0.06
    oco
    0.06
    Act Density 0.015%

    No Known Activations