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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ci
    -0.08
    ani
    -0.08
    _trait
    -0.07
     ділян
    -0.07
    otr
    -0.07
     proto
    -0.07
    iat
    -0.07
    iert
    -0.07
    mits
    -0.06
     versatility
    -0.06
    POSITIVE LOGITS
     $
    0.14
    ($
    0.10
     ($
    0.10
     £
    0.09
    :$
    0.08
    ;$
    0.08
     dollar
    0.08
    ,$
    0.07
    $
    0.07
     [$
    0.07
    Act Density 0.148%

    No Known Activations