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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '%
    -0.07
    .warning
    -0.07
    _ability
    -0.07
    ']=='
    -0.06
    แรก
    -0.06
     sabah
    -0.06
     bombing
    -0.06
    _Z
    -0.06
    =id
    -0.06
    _tracker
    -0.06
    POSITIVE LOGITS
    -existing
    0.06
     aqu
    0.06
    rowning
    0.06
    Re
    0.06
    Towards
    0.06
    erais
    0.06
    AVOR
    0.06
     Advocate
    0.05
     informatie
    0.05
    ὰ
    0.05
    Act Density 0.023%

    No Known Activations