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

    Neuronpedia

    INDEX
    Explanations

    programming questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fuß
    -0.08
    auté
    -0.07
     chuckled
    -0.07
    rollers
    -0.07
     slammed
    -0.07
    Ma
    -0.07
     ödül
    -0.07
    情報を
    -0.07
    맘
    -0.07
     humour
    -0.07
    POSITIVE LOGITS
    粤港澳
    0.08
    .setAlignment
    0.07
     substantially
    0.07
     IPv
    0.07
    全天
    0.07
    ราช
    0.07
    otropic
    0.07
    о�
    0.07
    apse
    0.07
     обеспечива
    0.07
    Act Density 0.056%

    No Known Activations