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

    Neuronpedia

    INDEX
    Explanations

    movement verbs and destinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uitvo
    0.80
     مقصد
    0.71
    љу
    0.67
     Justus
    0.64
     forcefully
    0.64
    ကား
    0.64
     обратно
    0.64
    Inbox
    0.64
    샛
    0.64
     Naik
    0.63
    POSITIVE LOGITS
    පු
    0.86
     spacing
    0.81
     वु
    0.79
     depict
    0.79
     see
    0.78
     brainstorming
    0.77
    proofing
    0.77
     قد
    0.74
     See
    0.73
     networking
    0.73
    Act Density 0.043%

    No Known Activations