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

    Neuronpedia

    INDEX
    Explanations

    ometers and metrics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -II
    -0.08
    pos
    -0.07
    Ghost
    -0.07
     assim
    -0.07
    .drawImage
    -0.07
    iking
    -0.07
    疮
    -0.07
     Placeholder
    -0.07
     Git
    -0.06
    Proposal
    -0.06
    POSITIVE LOGITS
    指出
    0.07
    才干
    0.07
     SMB
    0.07
    cient
    0.07
    _PTR
    0.07
     UIResponder
    0.07
    奥地
    0.07
    瑞士
    0.07
    观测
    0.06
     CDC
    0.06
    Act Density 0.021%

    No Known Activations