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

    Neuronpedia

    INDEX
    Explanations

    signs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    احث
    -0.07
     POSITION
    -0.07
     Laboratories
    -0.06
    orent
    -0.06
    Investigators
    -0.06
    azor
    -0.06
    �
    -0.06
    amaha
    -0.06
    εκ
    -0.06
     doctrines
    -0.06
    POSITIVE LOGITS
     signs
    0.09
     indications
    0.08
    -update
    0.07
     luck
    0.07
     tmp
    0.07
     Trace
    0.07
     weakening
    0.06
     traces
    0.06
     distinctly
    0.06
     classmates
    0.06
    Act Density 0.029%

    No Known Activations