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

    Neuronpedia

    INDEX
    Explanations

    scientific texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.81
     Normdatei
    -0.79
    lorette
    -0.70
     AssemblyCulture
    -0.68
    DebuggerNonUser
    -0.63
    LookAnd
    -0.62
    SequentialGroup
    -0.59
     يتيمه
    -0.59
    SPATH
    -0.58
    Билгалдахарш
    -0.57
    POSITIVE LOGITS
     echo
    0.81
     fake
    0.60
     tribal
    0.57
    echo
    0.56
    fake
    0.56
     alternative
    0.54
     confirmation
    0.53
     filter
    0.52
     Echo
    0.52
     division
    0.51
    Act Density 0.001%

    No Known Activations