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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     concealed
    -0.07
    823
    -0.07
     emissions
    -0.07
    ileges
    -0.06
    iping
    -0.06
    Metadata
    -0.06
     Lucy
    -0.06
     Emily
    -0.06
    visible
    -0.06
    assets
    -0.06
    POSITIVE LOGITS
    删除成功
    0.07
    #aa
    0.07
    xAC
    0.07
    CRET
    0.07
    _SID
    0.06
     ฟร
    0.06
     pParent
    0.06
    _Mode
    0.06
    如何
    0.06
    deş
    0.06
    Act Density 0.005%

    No Known Activations