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

    Neuronpedia

    INDEX
    Explanations

    Technical/Academic writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alus
    -0.28
    ç¦ģ
    -0.27
     Boundary
    -0.26
     S
    -0.26
    ÃĢ
    -0.26
    åĩºåĬ¨
    -0.26
    api
    -0.25
     Conf
    -0.25
    conf
    -0.24
    notice
    -0.24
    POSITIVE LOGITS
    ibble
    0.32
     garg
    0.28
    meld
    0.26
    _EL
    0.25
     phenomen
    0.25
    UTTON
    0.25
    .El
    0.25
     staffer
    0.25
    åıµ
    0.24
    ilogy
    0.24
    Act Density 3.036%

    No Known Activations