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

    Neuronpedia

    INDEX
    Explanations

    addSubview

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    יטת
    -0.07
    onomic
    -0.07
    ￫
    -0.07
     CSL
    -0.07
     McGr
    -0.07
     Capability
    -0.07
    聚会
    -0.07
    蜞
    -0.07
    亲情
    -0.07
    öt
    -0.07
    POSITIVE LOGITS
     improved
    0.08
     tops
    0.07
    끕
    0.07
     reduced
    0.07
     inconvenience
    0.07
    周
    0.07
     instructors
    0.07
    _PIXEL
    0.07
     arquivo
    0.07
     Supervisor
    0.07
    Act Density 0.002%

    No Known Activations