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

    Neuronpedia

    INDEX
    Explanations

    APS IPS ps

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arou
    -0.09
    Burn
    -0.08
    鲖
    -0.08
    缗
    -0.07
     Serbian
    -0.07
     Geneva
    -0.07
     foundations
    -0.07
     wspóln
    -0.07
     através
    -0.07
     notions
    -0.07
    POSITIVE LOGITS
     영화
    0.07
    놧
    0.07
    );
    0.06
    텦
    0.06
    ips
    0.06
    十四五
    0.06
    ']}</
    0.06
     ",";↵
    0.06
     fld
    0.06
    ﭰ
    0.06
    Act Density 0.014%

    No Known Activations