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

    Neuronpedia

    INDEX
    Explanations

    community centres, cohesion, focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hasher
    0.54
     carg
    0.52
     parking
    0.51
     parche
    0.51
    webview
    0.50
     tracker
    0.50
     definir
    0.47
    ctions
    0.47
    centric
    0.47
     trabajar
    0.46
    POSITIVE LOGITS
    "，
    0.47
    ازت
    0.47
     irmãos
    0.46
    h
    0.45
    。",
    0.44
    赈
    0.44
    )")
    0.43
     собы
    0.43
     Lomb
    0.43
     其
    0.42
    Act Density 0.000%

    No Known Activations