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

    Neuronpedia

    INDEX
    Explanations

    instances of "help" close to indicators of an individual or group either assisting or being assisted

    oai_token-act-pair · gemini-2.0-flash

    help

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tfsi
    -0.59
     étoit
    -0.59
    principalColumn
    -0.58
    providedIn
    -0.57
     mxArray
    -0.57
     auroit
    -0.56
     NUKAT
    -0.54
     feroit
    -0.53
     Infórmanos
    -0.53
    AddTagHelper
    -0.53
    POSITIVE LOGITS
     SwitchCompat
    0.63
     us
    0.62
     you
    0.61
     me
    0.57
     them
    0.56
     him
    0.56
    LayoutPanel
    0.53
    ContentAsync
    0.52
    balleur
    0.47
    期刊论文
    0.47
    Act Density 0.378%

    No Known Activations