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

    Neuronpedia

    INDEX
    Explanations

    been

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    负债
    -0.07
    펌
    -0.07
    _match
    -0.07
    _palette
    -0.07
    -select
    -0.06
     peter
    -0.06
    _attention
    -0.06
    csi
    -0.06
    """.
    -0.06
    ********************************************************************************
    -0.06
    POSITIVE LOGITS
    okit
    0.07
     erreur
    0.07
    ATFORM
    0.07
    lijk
    0.06
     Difference
    0.06
     supremacy
    0.06
    退款
    0.06
     flats
    0.06
    üss
    0.06
     conf
    0.06
    Act Density 0.031%

    No Known Activations