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

    Neuronpedia

    INDEX
    Explanations

    actions concerning others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    clature
    0.72
     కీలక
    0.67
    🐈
    0.67
    ަން
    0.66
     בכל
    0.66
    వల
    0.65
     કેટલી
    0.64
    +#+#
    0.64
    转型
    0.64
    طلح
    0.64
    POSITIVE LOGITS
     others
    3.96
     someone
    3.48
     Others
    3.47
    others
    3.40
    别人
    3.38
    Others
    3.37
     somebody
    3.15
    别人的
    3.11
    他人
    3.07
    其他人
    3.07
    Act Density 0.659%

    No Known Activations