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

    Neuronpedia

    INDEX
    Explanations

    LED video displays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mitral
    0.51
     cyclohexane
    0.49
     gradle
    0.44
     ferrugineux
    0.44
     eigenvalue
    0.44
     hydrochloric
    0.43
     alfalfa
    0.43
     mocha
    0.43
     electromagnet
    0.43
     trainable
    0.43
    POSITIVE LOGITS
    R
    0.61
    z
    0.59
    S
    0.57
    St
    0.55
    ý
    0.55
    Ch
    0.55
    L
    0.55
    i
    0.54
    P
    0.54
    W
    0.54
    Act Density 0.000%

    No Known Activations