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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ánh
    -0.08
    L
    -0.08
    were
    -0.07
    	case
    -0.07
    find
    -0.07
     Alaska
    -0.07
    allow
    -0.06
     WF
    -0.06
     Wales
    -0.06
    (',
    -0.06
    POSITIVE LOGITS
    .edge
    0.07
    מכשיר
    0.07
    羽毛
    0.07
     entityManager
    0.07
     변화
    0.07
    痛み
    0.07
    addPreferredGap
    0.07
    社科
    0.07
     engagement
    0.07
    .assignment
    0.07
    Act Density 0.073%

    No Known Activations