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

    Neuronpedia

    INDEX
    Explanations

    movable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     anni
    -0.07
    ิท
    -0.07
    _attack
    -0.07
    fft
    -0.07
     výše
    -0.07
    _lines
    -0.07
     courte
    -0.06
    ène
    -0.06
     hâl
    -0.06
    lerine
    -0.06
    POSITIVE LOGITS
     movable
    0.12
    145
    0.06
     �
    0.06
     Examples
    0.06
    _THROW
    0.06
    	email
    0.06
    	dev
    0.06
     Ricky
    0.06
    import
    0.06
     licked
    0.06
    Act Density 0.005%

    No Known Activations