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

    Neuronpedia

    INDEX
    Explanations

    costs and damages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Suicide
    -0.07
    .Mar
    -0.07
     เกม
    -0.06
    	i
    -0.06
     appliance
    -0.06
     Remote
    -0.06
     nursing
    -0.06
     sweet
    -0.06
     praise
    -0.06
    ombies
    -0.06
    POSITIVE LOGITS
    _cookies
    0.08
     pave
    0.07
     tinder
    0.07
     fromDate
    0.07
    ＞
    0.07
    ServletResponse
    0.07
    /control
    0.06
     �
    0.06
    \model
    0.06
    -members
    0.06
    Act Density 0.063%

    No Known Activations