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

    Neuronpedia

    INDEX
    Explanations

    specific

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	FOR
    -0.07
    LastError
    -0.06
    toast
    -0.06
     �
    -0.06
     Skill
    -0.06
     Mog
    -0.06
     mines
    -0.06
    Pid
    -0.06
    cancellationToken
    -0.06
     Herr
    -0.06
    POSITIVE LOGITS
     Publication
    0.07
     ardından
    0.07
    енням
    0.06
     ballistic
    0.06
     chiếm
    0.06
     sent
    0.06
    ạn
    0.06
    ceso
    0.06
    ùa
    0.06
     supernatural
    0.06
    Act Density 0.001%

    No Known Activations