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

    Neuronpedia

    INDEX
    Explanations

    dashes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     estim
    -0.07
    	i
    -0.06
    +l
    -0.06
     al
    -0.06
    Tree
    -0.06
    块
    -0.06
    clinic
    -0.06
    BigInt
    -0.06
     обра
    -0.06
    _hub
    -0.06
    POSITIVE LOGITS
    .vn
    0.06
     sculpt
    0.06
    (KEY
    0.06
     Low
    0.06
     enlarged
    0.06
    ophobia
    0.06
     hired
    0.06
    arrison
    0.06
    /control
    0.06
     Tough
    0.06
    Act Density 0.004%

    No Known Activations