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

    Neuronpedia

    INDEX
    Explanations

    itative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    typ
    -0.07
     finden
    -0.07
    -looking
    -0.07
     userinfo
    -0.06
     elektron
    -0.06
    	ti
    -0.06
     tracking
    -0.06
     reduction
    -0.06
     protector
    -0.06
    кових
    -0.06
    POSITIVE LOGITS
    itative
    0.16
    atively
    0.07
    eful
    0.07
    reglo
    0.07
    ATIVE
    0.07
    еств
    0.07
    юн
    0.06
     Deutsche
    0.06
     Veterans
    0.06
    ेट
    0.06
    Act Density 0.001%

    No Known Activations