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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yaptır
    -0.06
    _VLAN
    -0.06
    URE
    -0.06
    Ingrese
    -0.06
    ía
    -0.06
    gregar
    -0.06
     �
    -0.06
     ↵↵
    -0.06
    _Normal
    -0.06
    .Types
    -0.06
    POSITIVE LOGITS
    乃
    0.07
    -striped
    0.07
    (IN
    0.07
     самостоятельно
    0.07
    .IOException
    0.07
    μιλος
    0.06
     emptied
    0.06
    ีพ
    0.06
     detach
    0.06
    icemail
    0.06
    Act Density 0.008%

    No Known Activations