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

    Neuronpedia

    INDEX
    Explanations

    cognitive development

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lug
    -0.08
    楙
    -0.08
     Hệ
    -0.07
     grasp
    -0.07
    ën
    -0.07
    千伏
    -0.07
    ’d
    -0.07
     семей
    -0.06
    _WP
    -0.06
    Mb
    -0.06
    POSITIVE LOGITS
    FSIZE
    0.07
    痛
    0.07
    _CHANNEL
    0.07
    _$_
    0.07
    _CONTROLLER
    0.06
    报警
    0.06
    歌
    0.06
     blanco
    0.06
    投资
    0.06
    Sizes
    0.06
    Act Density 0.019%

    No Known Activations