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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    515
    -0.09
    ;',
    -0.08
    	HANDLE
    -0.07
    sigma
    -0.06
    接
    -0.06
     IDirect
    -0.06
    505
    -0.06
    508
    -0.06
    ubber
    -0.06
    ㎡
    -0.06
    POSITIVE LOGITS
     restless
    0.06
     CLEAR
    0.06
     Offline
    0.06
     vulner
    0.06
    gage
    0.06
    gregar
    0.06
    عب
    0.06
    romo
    0.06
    ым
    0.06
    Stopped
    0.06
    Act Density 0.000%

    No Known Activations