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

    Neuronpedia

    INDEX
    Explanations

    Safety warnings/directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     POP
    -0.07
    }')
    -0.06
     Char
    -0.06
     validates
    -0.06
    NP
    -0.06
    )o
    -0.06
     SNAP
    -0.06
    刺
    -0.06
    ']").
    -0.06
    -0.06
    POSITIVE LOGITS
     исп
    0.07
     콘
    0.06
    �权
    0.06
    possible
    0.06
     undecided
    0.06
     поє
    0.06
     обращ
    0.06
    클
    0.06
     NotImplementedException
    0.06
     Pause
    0.06
    Act Density 0.005%

    No Known Activations