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

    Neuronpedia

    INDEX
    Explanations

    itemized lists

    oai_token-act-pair · gemini-2.0-flash

    bulleted list text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ;
    -0.50
    iconque
    -0.50
    (++
    -0.50
    ]);
    -0.50
     male
    -0.50
     ích
    -0.49
    ]]);
    -0.49
    ])
    -0.48
     (
    -0.48
    ]];
    -0.48
    POSITIVE LOGITS
    脚注の使い方
    0.85
     незавершена
    0.77
    antaranya
    0.71
    Enllaces
    0.70
     NgModule
    0.66
     виправивши
    0.66
     esternos
    0.65
     ligiloj
    0.65
    astify
    0.65
    parsedMessage
    0.65
    Act Density 0.512%

    No Known Activations