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

    Neuronpedia

    INDEX
    Explanations

    list

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CentOS
    -0.07
     SCR
    -0.07
    -deals
    -0.07
    remely
    -0.06
    _hostname
    -0.06
     áll
    -0.06
    änd
    -0.06
     allotted
    -0.06
     kariy
    -0.06
    preferences
    -0.06
    POSITIVE LOGITS
                         ↵
    0.07
    -'.$
    0.07
     createDate
    0.06
    omet
    0.06
    sil
    0.06
     clauses
    0.06
     ung
    0.06
    Weapons
    0.06
    .args
    0.06
    pieces
    0.06
    Act Density 0.021%

    No Known Activations